Print

Print
Thank you Eugene

However, I still don't understand where my between subjects design is... for the example you suggested it seems that all the subjects are different (right?), but for my design I have the same subjects twice.. meaning: 

ControlSubject1-T1
ControlSubject1-T2
ControlSubject2-T1
ControlSubject2-T2
.
.
.
PatientSubject1-T1
PatientSubject1-T2
PatientSubject2-T1
PatientSubject2-T2
.
.
.

So, if I understand correctly a 2-factor 2-level design for me it will be Factor A (Group: controls, patients) and Factor B (Time: time1, time2) ? But what about the fact that each subject is repeated? I have 58 subjects, 14 in Control group but scanned twice so its 28 subjects, and 15 in Patient scanned twice so 30 subjects. so they are not 58 different subjects, its 29 subjects twice. Will that fit the Anova 2 factors 2-levels? and if so, how??  

Thank you
Salomi

On Oct 28, 2009, at 11:33 AM, Eugene Duff wrote:

Hi Salomi
I think the ANOVA 2-factors 2-levels example on the FEAT details page is pretty close to what you want?  
Eugene 

2009/10/28 Salomi <[log in to unmask]>
Hello all

Being new with FSL: I 've been searching the FSL tutorials and on previous emails but
couldn't find anything regarding how to set up a mixed model in GLM qui. I have 2 groups
(control, patient), scanned twice (T1, T2) and I want to generate a design matrix and
contrast files. What is confusing is how to setup the design so I can get an interaction of
group X time.

For example if it was only repeated measures of the same group I would do something
like this (for 2 subjects):

1 0 1 0
1 0 0 1
0 1 1 0
0 1 0 1

right?

Now that I have 2 groups repeated and want to see the interaction, how should I design
it?

Any help will be much appreciated,
Thank you
Salomi



--
Eugene Duff

Centre for Functional MRI of the Brain (FMRIB)
University of Oxford
John Radcliffe Hospital, Headington OX3 9DU  Oxford  UK

Ph: +44 (0) 1865 222 523  Fax: +44 (0) 1865 222 717

--


This message has been checked for viruses but the contents of an attachment may still contain software viruses, which could damage your computer system: you are advised to perform your own checks. Email communications with the University of Nottingham may be monitored as permitted by UK legislation.